Daan MeijerandClaude Fable 5.1
f537add573
jsonb_to_recordset declared hash16k as text; against the char(32) column the join cast the column, so Postgres scanned all of file_hashes for every call (4 s, 20 calls a minute: 44% of the database's time). Declared char(32), the join walks file_hashes_hash_size_release_idx: 24 ms for 300 pairs. LOG.md (138). Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
30 lines
1.5 KiB
TypeScript
30 lines
1.5 KiB
TypeScript
import db from '@adonisjs/lucid/services/db'
|
|
|
|
/**
|
|
* Twins by content (LOG.md (130)): a probed file's first 16 KiB and size (file_hashes, what the par2 merge and the
|
|
* repeated verdict match) in a catalog release that has a name, readable or found inside. The same film posted
|
|
* under scrambles by other tools gets that name without another fetch. Releases with a junk verdict don't count.
|
|
*/
|
|
export async function twinNames(
|
|
pairs: { hash16k: string; size: number }[],
|
|
trx: { rawQuery: typeof db.rawQuery } = db
|
|
): Promise<Map<string, string>> {
|
|
const out = new Map<string, string>()
|
|
if (pairs.length === 0) return out
|
|
// hash16k typed as the column (char(32)): as text the join cast the column and scanned all of file_hashes
|
|
// instead of file_hashes_hash_size_release_idx, 4 s a call (LOG.md (138)).
|
|
const { rows } = await trx.rawQuery(
|
|
`SELECT DISTINCT ON (h.hash16k, h.size) h.hash16k, h.size, coalesce(r.inner_name, r.name) AS name
|
|
FROM jsonb_to_recordset(?::jsonb) AS v(hash16k char(32), size bigint)
|
|
JOIN file_hashes h ON h.hash16k = v.hash16k AND h.size = v.size
|
|
JOIN releases r ON r.id = h.release_id AND (r.readable OR r.inner_name IS NOT NULL)
|
|
WHERE NOT EXISTS (SELECT 1 FROM release_verdicts x WHERE x.release_id = r.id)
|
|
ORDER BY h.hash16k, h.size, r.readable DESC, r.id`,
|
|
[JSON.stringify(pairs)]
|
|
)
|
|
for (const r of rows) out.set(`${r.hash16k}\t${r.size}`, r.name)
|
|
return out
|
|
}
|
|
|
|
export const twinKey = (hash16k: string, size: number) => `${hash16k}\t${size}`
|